The Australian Centre for Visual Technologies

Seminar led by Prof Peter Olver, University of Minnesota – Wednesday 14th March 2012

Pru — Thu, 16 Feb 2012 06:19:00 +0000

The ACVT is pleased to welcome Professor Peter Olver, from the University of Minnesota, who will be visiting on Wednesday 14th March 2012.

Prof Olver will lead the below seminar, to be held in the basement of the Ingkarni Wardli building, B18 Teaching Suite 2 at 3.10pm.

Title: Invariant histograms and signatures for object recognition and symmetry detection

Abstract: Prof Olver will survey recent developments in the use of group-invariant histograms, using distances, areas, etc., and signatures, using differential invariants, joint invariants, invariant numerical approximations, etc., for object recognition and symmetry detection in images.

Bio: http://www.math.umn.edu/~olver/

Professor Ian Reid appointed from September 2012

Pru — Tue, 31 Jan 2012 04:30:37 +0000

The Australian Centre for Visual Technologies is pleased to announce the appointment of Professor Ian Reid from September 2012. Ian is currently a Professor of Engineering Science, running the Active Vision Group at the University of Oxford and will bring to the University of Adelaide an internationally recognised research record in the areas of Computer Vision and visual technologies.

Professor Reid’s appointment will ensure that the School of Computer Science remains at the leading edge of international research and teaching.

This is an exciting appointment for the ACVT and the School of Computer Science and we look forward to welcoming Professor Reid when he joins the University later this year!

‘Best Colour Paper’ awarded to David Sandberg

Pru — Wed, 14 Dec 2011 04:46:20 +0000

Congratulations to David Sandberg, programmer for SNAP Network Surveillance, who has won the ‘Best Colour Paper’ prize awarded by Canon Information Systems Research Australia (CiSRA) at the recent 2011 DICTA conference.

David’s paper, ‘Model-Based Video Coding using Colour and Depth Cameras’ can be viewed here sandberg_dicta11[1]

ACVT hosts model-fitting seminars, Monday 12th December 2011

Pru — Mon, 05 Dec 2011 04:45:38 +0000

On Monday 12th December, the ACVT welcomes two visitors:

Professor Kenichi Kanatani, Professor of Computer Science at Okayama University, Japan, and

Dr Andrew Comport, “Chargé de Recherches” (Tenure Researcher) with the Centre National de Recherche Scientifique (CNRS) in France.

Along with Professor Wojciech Chojnacki, Senior Research Fellow in the School of Computer Science at The University of Adelaide, each will present a model-fitting seminar during the day:

Venue: North Tce Campus, Innova 21 Building, B21 Teaching Suite 5, Basement Level

10.30am: Prof Wojciech Chojnacki will present, ‘Multiple Homography Estimation Using Latent Variables’

2.00pm: Dr Andrew Comport will present, ‘Dense visual localisation and mapping in real-time’

3.30pm: Prof Kenichi Kanatani will present, ‘Renormalization Returns! Hyper-renormalization and its Applications’

Please see Computer Science Seminars – 12th Dec 2011 for details on each of the above seminars.

The 2011 Pacific-Rim Conference on Multimedia – Keynote Speech

Pru — Mon, 05 Dec 2011 04:19:17 +0000

Prof van den Hengel has been invited to give a keynote speech at this year’s Pacific-Rim Conference on Multimedia (PCM) to be held from 20th – 22nd Dec 2011 in Sydney.

Pacific-Rim Conference on Multimedia (PCM) is a major annual international conference organized as a forum for the dissemination of state-of-the-art technological advances and research results in the fields of theoretical, experimental, and applied multimedia analysis and processing. The proceedings of the conference will be published in a book series of Lecture Notes in Computer Science by Springer, and available in the ISI Web of Knowledge.PCM 2011 is the 12th conference in this highly successful and increasingly influential series and will feature opening keynote addresses, invited plenary talks, tutorials, special sessions, and technical presentations of refereed papers.

Prof van den Hengel will be discussing 3D User Created Content.

For more information on the conference and Prof van den Hengel’s keynote speech, please visit http://pcm2011.org/

ACVT welcomes Professor Ba-Ngu Vo, UWA

Pru — Mon, 05 Dec 2011 04:02:36 +0000

On Monday 5^th December, the School of Computer Science and the ACVT welcomes Professor Ba-Ngu Vo, from the University of WA. He will be leading the below seminar:

Title: Error metric for multi-object estimation.

Abstract: The concept of a miss-distance, or error, between a reference quantity and its estimated value, plays a fundamental role in any estimation/filtering problem. However, this is a rather under-rated topic in the well-established field of multi-object estimation/filtering. Indeed, until recently, there was no satisfactory notion of an error metric. This presentation discusses multi-object representation and various multi-object metrics, in particular, the inconsistencies of a number of existing multi-object metrics and how these inconsistencies can be resolved with the Optimal Sub-Pattern Assignment (OSPA) metric.

About the Speaker: Prof Vo is the Winthrop Professor and Chair of Signal Processing in the School of Electrical, Electronic and Computer Engineering at the University of Western Australia. His research interests are Signal Processing, Systems Theory and Stochastic Geometry with emphasis on target tracking, robotics and computer vision.

Time: 3:10pm

Venue: Room 5.57 – Level 5 Innova 21 Building

2011 Pearcey SA Entrepreneur Award – Runner Up

Pru — Mon, 21 Nov 2011 22:44:08 +0000

Congratulations to Dr Henry Detmold who was Runner Up in the 2011 Pearcey SA Entrepreneur Award!

The Entrepreneur Award is a State award, rolling up into the Benson National ICT Entrepreneur of the Year Award, and is aimed at encouraging and rewarding fresh and innovative talent in the ICT and Digital Media professions

Henry was awarded a special mention for his contribution as Founder and CTO of SNAP (Snap Network Survelliance Pty Ltd) http://www.snapsurveillance.com/.

Well done Henry!

The Australian Summit on 3D Multimedia – Invited Presentation

Pru — Mon, 21 Nov 2011 02:27:34 +0000

Prof van den Hengel has been invited to attend the Australian Summit on 3D Multimedia, held in Wollongong in December 2011.

This two-day event includes invited presentations by international and Australian experts from both academic research institutions and the industry. The Summit is the premier forum presenting the leading edge advances in 3D multimedia acquisition, analysis, presentation, visualization and display technologies, as well as the emerging new applications and services.

Prof van den Hengel will be discussing 3D User Created Content.

For more information on the Summit and details of Prof van den Hengel’s talk, please visit http://ictr.uow.edu.au/au3dmm11/index.html

$1.4m in ARC funding for research over the next 3 – 4 years

Pru — Wed, 16 Nov 2011 00:48:45 +0000

In addition to the success of securing Discovery Project funding and DECRA funding in the 2012 round, the ACVT has secured over $770,000 in funding for an ARC Future Fellowship, awarded to Associate Prof Andrew Bradley. This is a total of over $1.4m of funding for research for the Centre over the next 3 – 4 years. Well done!!

A/Prof Bradley’s project will contribute to the next generation of virtual microscopy systems that provide innovative features capable of significantly increasing the adoption of digitial imaging technology throughout the field of diagnostic pathology. These tools will especially contribute to the screening and diagnosis of cervical, lung and bladder cancer.

DECRA Success! Congratulations to Dr Javen Shi

Pru — Tue, 15 Nov 2011 01:21:14 +0000

Well done to Javen who has been awarded $375,00o of DECRA funding through the ARC in the 2012 round!! Only 277 proposals were awarded from over 2,100 applications. This is a fabulous result for Javen, congratulations!

Title: Compressive sensing based probabilistic graphical models (PGM)

Project Summary: The aim of the project is to develop fast, large scale probabilistic graphical models (PGM) learning and inference methods. The resulting system will be able to process large scale PGMs on a standard PC, and will be easily extendable to computer clustering for larger scale PGMs requiring higher precision.